# FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data

arXiv: https://arxiv.org/abs/2507.10540 · HTML: https://mlsanity.com/paper/2507.10540/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 79 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 30 of 63)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)

## Built on by (most cited first, 10 of 10)

- [R2-Router: A New Paradigm for LLM Routing with Reasoning](https://mlsanity.com/paper/2602.02823/) (2026)
- [GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs](https://mlsanity.com/paper/2604.23626/) (2026)
- [Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs](https://mlsanity.com/paper/2602.07276/) (2026)
- [LLM Router: Rethinking Routing with Prefill Activations](https://mlsanity.com/paper/2603.20895/) (2026)
- [Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization](https://mlsanity.com/paper/2604.15022/) (2026)
- [InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation](https://mlsanity.com/paper/2510.09724/) (2025)
- [PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling](https://mlsanity.com/paper/2511.16883/) (2025)
- [Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems](https://mlsanity.com/paper/2602.11877/) (2026)
- [Picking the Right Specialist: Attentive Neural Process-based Selection of Task-Specialized Models as Tools for Agentic Healthcare Systems](https://mlsanity.com/paper/2602.14901/) (2026)
- [Can Heterogeneous Language Models Be Fused?](https://mlsanity.com/paper/2604.01674/) (2026)

## Abstract (arXiv)

The rapid advancement of large language models (LLMs) has created a diverse landscape of models, each excelling at different tasks. This diversity drives researchers to employ multiple LLMs in practice, leaving behind valuable multi-LLM log data. This naturally leads to the question of whether such logs can be fully leveraged to fuse LLMs' complementary capabilities. Although prior work has explored various strategies for integrating multiple LLMs, we argue that practical fusion must meet two essential requirements: (1) compatibility with real-world serving scenarios (e.g., local and API-based serving), and (2) flexibility to operate at different stages of the LLM pipeline to meet varied user needs (e.g., fine-tuning and inference stages). To this end, we introduce LLMFusionBench, a large-scale benchmark for LLM fusion that spans 14 tasks across five domains, with responses from 20 open-source LLMs (8B--671B) totaling 103M tokens. Building on LLMFusionBench, we propose FusionFactory, a systematic framework with three elaborated levels: (1) query-level fusion via tailored LLM routers, (2) thought-level fusion leveraging retrieved abstract reasoning templates, and (3) model-level fusion via distillation from top-ranked responses. Experiments show that FusionFactory consistently outperforms the best individual LLM across all 14 benchmarks, with the optimal fusion configuration varying across benchmarks, highlighting the promise of multi-LLM log data as a practical foundation for fusing diverse LLM capabilities.